Summary of Evaluating the Performance-deviation Of Itemknn in Recbole and Lenskit, by Michael Schmidt et al.
Evaluating the performance-deviation of itemKNN in RecBole and LensKit
by Michael Schmidt, Jannik Nitschke, Tim Prinz
First submitted to arxiv on: 18 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The study compares the performance of item-based k-Nearest Neighbors (ItemKNN) algorithms in two popular recommender system libraries: RecBole and LensKit. The authors evaluate their efficiency, accuracy, and scalability using four datasets: Anime, Modcloth, ML-100K, and ML-1M. They focus on normalized discounted cumulative gain (nDCG) as the primary metric. Results show that RecBole outperforms LensKit in terms of nDCG, precision, and recall for two datasets. However, after adjusting LensKit’s nDCG calculation to match RecBole’s method, both libraries showed similar performance. The study identifies differences in similarity matrix calculations as the main cause of performance deviations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper compares two computer programs that help recommend items to people based on what they like. They tested these programs using different types of data and found that one program did better than the other on some tests, but only because it was doing things slightly differently. When they made both programs do things the same way, they performed similarly well. |
Keywords
* Artificial intelligence * Precision * Recall
